[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-claude-office-skills-transcription-automation-zh-CN":3,"guides-for-claude-office-skills-transcription-automation":224,"similar-k17dj7ajf0w4cb3z4qw4khc5v18662n4":225},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":189,"isFallback":194,"parentExtension":195,"providers":196,"relations":201,"repo":203,"workflow":221},1778053148350.4788,"k17dj7ajf0w4cb3z4qw4khc5v18662n4",[],{"reviewCount":8},0,{"description":10,"name":11,"sourceUrl":12,"tags":13},"Automate audio/video transcription, meeting notes, subtitle generation, and content processing","Transcription Automation","https://github.com/claude-office-skills/skills/tree/HEAD/transcription-automation",[14,15,16,17,18,19,20],"transcription","audio","video","meetings","subtitles","multimedia","mcp",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":178,"workflow":187},1778053561145.7756,"kn75deqd7c21f5vtgae9xh82258675qf","en",{"checks":26,"evaluatedAt":168,"extensionSummary":169,"promptVersionExtension":170,"promptVersionScoring":171,"rationale":172,"score":173,"summary":174,"tags":175,"targetMarket":176,"tier":177},[27,32,35,38,42,45,49,53,56,59,63,68,72,76,79,82,85,88,91,94,98,102,106,110,114,117,120,123,127,130,133,136,139,142,146,149,152,155,158,161,165],{"category":28,"check":29,"severity":30,"summary":31},"Practical Utility","Problem relevance","pass","The description clearly states the user problem: automating audio/video transcription, meeting notes, subtitle generation, and content processing.",{"category":28,"check":33,"severity":30,"summary":34},"Unique selling proposition","The extension offers specialized workflows and configuration options for transcription and subtitle generation, going beyond basic LLM capabilities by integrating with specific engines like Whisper, AssemblyAI, and Deepgram, and providing structured output formats.",{"category":28,"check":36,"severity":30,"summary":37},"Production readiness","The skill outlines comprehensive pipelines for transcription and subtitle generation, including pre-processing, engine selection, post-processing, and integration workflows for Zoom, YouTube, and podcasts, covering the complete lifecycle of audio/video content processing.",{"category":39,"check":40,"severity":30,"summary":41},"Scope","Single responsibility principle","The extension focuses on audio/video transcription and related content processing tasks, with clear sub-workflows for transcription, meeting notes, and subtitle generation, without branching into unrelated domains.",{"category":39,"check":43,"severity":30,"summary":44},"Description quality","The 'Displayed Description' accurately reflects the skill's capabilities for automating audio/video transcription, meeting notes, subtitle generation, and content processing.",{"category":46,"check":47,"severity":30,"summary":48},"Invocation","Scoped tools","The MCP tools listed (whisper_transcribe, assembly_ai, deepgram_api, subtitle_generate) are specific to the transcription and subtitle domain, indicating a good level of scoping.",{"category":50,"check":51,"severity":30,"summary":52},"Documentation","Configuration & parameter reference","The SKILL.md provides detailed YAML configuration blocks for transcription, meeting notes, speaker diarization, and subtitle generation, outlining most relevant settings and their potential values.",{"category":39,"check":54,"severity":30,"summary":55},"Tool naming","The listed MCP tools (whisper_transcribe, assembly_ai, deepgram_api, subtitle_generate) are descriptive and aligned with the domain.",{"category":39,"check":57,"severity":30,"summary":58},"Minimal I/O surface","Configuration examples show specific parameters for transcription and subtitle generation, suggesting inputs are focused on the task's needs, and outputs are structured as text transcripts or subtitle files.",{"category":60,"check":61,"severity":30,"summary":62},"License","License usability","The extension includes a standard MIT license file, which is a permissive open-source license.",{"category":64,"check":65,"severity":66,"summary":67},"Maintenance","Commit recency","warning","There are no commits on the default branch (pushedAt: n/a), indicating the extension may be unmaintained.",{"category":64,"check":69,"severity":70,"summary":71},"Dependency Management","not_applicable","No third-party dependencies were identified within the provided skill code, making this check not applicable.",{"category":73,"check":74,"severity":70,"summary":75},"Security","Secret Management","The provided code does not appear to handle or expose any secrets.",{"category":73,"check":77,"severity":30,"summary":78},"Injection","No obvious signs of insecure loading or execution of third-party data were found in the provided markdown.",{"category":73,"check":80,"severity":30,"summary":81},"Transitive Supply-Chain Grenades","The skill does not appear to fetch remote code or data at runtime, and all content seems to be bundled within the skill directory.",{"category":73,"check":83,"severity":30,"summary":84},"Sandbox Isolation","The skill does not appear to make any assumptions or modifications outside of its designated scope or project folder.",{"category":73,"check":86,"severity":30,"summary":87},"Sandbox escape primitives","No detached process spawns or retry loops around denied tool calls were identified.",{"category":73,"check":89,"severity":30,"summary":90},"Data Exfiltration","No suspicious outbound calls or references to confidential data were found.",{"category":73,"check":92,"severity":30,"summary":93},"Hidden Text Tricks","The bundled content does not contain any hidden steering tricks, invisible characters, or other obfuscation methods.",{"category":95,"check":96,"severity":30,"summary":97},"Hooks","Opaque code execution","The skill's code and instructions are in plain markdown and configuration, with no signs of obfuscation or dynamic code execution.",{"category":99,"check":100,"severity":70,"summary":101},"Portability","Structural Assumption","The skill does not appear to make any assumptions about user-specific project organization outside of its own bundle.",{"category":103,"check":104,"severity":70,"summary":105},"Trust","Issues Attention","Issue data is not available (n/a for both opened and closed issues), so engagement cannot be assessed.",{"category":107,"check":108,"severity":30,"summary":109},"Versioning","Release Management","A version ('1.0.0') is declared in the SKILL.md frontmatter.",{"category":111,"check":112,"severity":30,"summary":113},"Code Execution","Validation","Configuration examples demonstrate structured input parameters for various aspects of transcription and subtitle generation, implying schema validation.",{"category":73,"check":115,"severity":70,"summary":116},"Unguarded Destructive Operations","The skill appears to be read-only and analytical, with no destructive operations identified.",{"category":111,"check":118,"severity":30,"summary":119},"Error Handling","The configuration examples imply structured error handling and reporting through the use of specific settings and output formats.",{"category":111,"check":121,"severity":70,"summary":122},"Logging","This skill does not appear to involve destructive actions or outbound calls that would necessitate local audit logging.",{"category":124,"check":125,"severity":70,"summary":126},"Compliance","GDPR","The skill processes audio/video content and does not appear to handle personal data directly, making GDPR compliance not directly applicable.",{"category":124,"check":128,"severity":30,"summary":129},"Target market","The skill supports multiple languages (en, zh, multi) and workflows applicable globally, with no regional restrictions detected. Target market is global.",{"category":99,"check":131,"severity":30,"summary":132},"Runtime stability","The skill's portability is supported by its use of standard transcription engines and common output formats, with no apparent OS or environment-specific assumptions.",{"category":46,"check":134,"severity":30,"summary":135},"Precise Purpose","The skill clearly defines its purpose (automate transcription, meeting notes, subtitles) and when to use it, including input and output formats.",{"category":46,"check":137,"severity":30,"summary":138},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the skill's core capabilities, including trigger phrases and output formats.",{"category":50,"check":140,"severity":30,"summary":141},"Concise Body","The SKILL.md body is well-structured with distinct sections for workflows, configurations, and examples, keeping it under a reasonable length and facilitating progressive disclosure.",{"category":143,"check":144,"severity":30,"summary":145},"Context","Progressive Disclosure","The SKILL.md uses YAML blocks and diagrams to outline workflows and configurations, and it links to API examples, demonstrating progressive disclosure.",{"category":143,"check":147,"severity":70,"summary":148},"Forked exploration","The skill is task-oriented and does not involve deep code review or extensive exploration, making 'context: fork' not applicable.",{"category":28,"check":150,"severity":30,"summary":151},"Usage examples","The SKILL.md includes clear YAML examples for various configurations (transcription, meeting notes, subtitles) and Python code snippets for interacting with Whisper and AssemblyAI.",{"category":28,"check":153,"severity":30,"summary":154},"Edge cases","The skill documentation implicitly handles edge cases through detailed configuration options for engines, audio settings, and output formats, allowing users to tailor the process.",{"category":111,"check":156,"severity":30,"summary":157},"Tool Fallback","The skill lists 'whisper_transcribe', 'assembly_ai', and 'deepgram_api' as tools and mentions the 'whisper' engine in configurations, implying these are optional and the 'whisper' engine can act as a fallback if others are unavailable.",{"category":99,"check":159,"severity":30,"summary":160},"Stack assumptions","The skill assumes standard audio/video file inputs and common transcription engines/formats, with no explicit OS or framework dependencies mentioned beyond the MCP server.",{"category":162,"check":163,"severity":30,"summary":164},"Safety","Halt on unexpected state","The detailed configuration options and workflow structures imply that unexpected states would halt the process and require user intervention or re-configuration.",{"category":99,"check":166,"severity":30,"summary":167},"Cross-skill coupling","The skill is self-contained and focused on transcription and related tasks, with no implicit reliance on other skills. Related skills are cross-referenced by name, not implicitly invoked.",1778053495220,"This skill automates audio and video transcription, generates meeting notes with speaker diarization, and creates various subtitle formats (SRT, VTT). It supports multiple transcription engines (Whisper, AssemblyAI, Deepgram) and offers detailed configuration for audio settings, language detection, and output features.","2.0.0","3.4.0","The extension is well-documented, covers its domain comprehensively, and provides detailed configuration options and examples. The only warning is due to the lack of recent commits, suggesting potential maintenance gaps.",92,"A comprehensive and well-documented skill for automating audio/video transcription, meeting notes, and subtitle generation.",[14,15,16,17,18,19,20],"global","verified",{"codeQuality":179,"collectedAt":180,"documentation":181,"maintenance":183,"security":184,"testCoverage":186},{},1778053485486,{"descriptionLength":182,"readmeSize":8},94,{},{"hasNpmPackage":185,"smitheryVerified":185},false,{"hasCi":185,"hasTests":185},{"updatedAt":188},1778053561145,{"githubOwner":190,"githubRepo":191,"locale":24,"slug":192,"type":193},"claude-office-skills","skills","transcription-automation","skill",true,null,{"extract":197,"llm":200},{"commitSha":198,"license":199},"9c4c7d5cd2813a8936bf2c9fdb174ea883b85a11","MIT",{"promptVersionExtension":170,"promptVersionScoring":171,"score":173,"targetMarket":176,"tier":177},{"repoId":202},"kd7fw7xbj58qc2z8whrrjptbed8659db",{"_creationTime":204,"_id":202,"identity":205,"providers":207,"workflow":218},1777995558409.8474,{"githubOwner":190,"githubRepo":191,"sourceUrl":206},"https://github.com/claude-office-skills/skills",{"discover":208,"github":211},{"sources":209},[210],"skills-sh",{"closedIssues90d":8,"forks":212,"license":199,"openIssues90d":213,"pushedAt":214,"readmeSize":215,"stars":216,"topics":217},27,2,1769868236000,29630,98,[],{"discoverAt":219,"extractAt":220,"githubAt":220,"updatedAt":220},1777995558409,1778053155657,{"anyEnrichmentAt":222,"extractAt":223,"githubAt":222,"llmAt":188,"updatedAt":188},1778053151766,1778053148350,[],[226,257,283,310,326,355],{"_creationTime":227,"_id":228,"community":229,"display":230,"identity":242,"providers":246,"relations":251,"workflow":253},1778054812528.7214,"k17c4avaab2db2m79et4f4hnwn867qj1",{"reviewCount":8},{"description":231,"installMethods":232,"name":233,"sourceUrl":234,"tags":235},"Multimodal AI processing via Google Gemini API (2M tokens context). Capabilities: audio (transcription, 9.5hr max, summarization, music analysis), images (captioning, OCR, object detection, segmentation, visual Q&A), video (scene detection, 6hr max, YouTube URLs, temporal analysis), documents (PDF extraction, tables, forms, charts), image generation (text-to-image, editing). Actions: transcribe, analyze, extract, caption, detect, segment, generate from media. Keywords: Gemini API, audio transcription, image captioning, OCR, object detection, video analysis, PDF extraction, text-to-image, multimodal, speech recognition, visual Q&A, scene detection, YouTube transcription, table extraction, form processing, image generation, Imagen. Use when: transcribing audio/video, analyzing images/screenshots, extracting data from PDFs, processing YouTube videos, generating images from text, implementing multimodal AI features.",{},"AI Multimodal Processing Skill","https://github.com/samhvw8/dot-claude/tree/HEAD/skills/ai-multimodal",[236,237,15,238,16,239,240,241,14],"gemini-api","multimodal","image","document-processing","text-to-image","ocr",{"githubOwner":243,"githubRepo":244,"locale":24,"slug":245,"type":193},"samhvw8","dot-claude","ai-multimodal",{"extract":247,"llm":249},{"commitSha":248,"license":199},"28c76162116d2eedab131c0e1548fdc76a2999f7",{"promptVersionExtension":170,"promptVersionScoring":171,"score":250,"targetMarket":176,"tier":177},95,{"repoId":252},"kd79ad9dpqazy79y2s6rvajgjn865xek",{"anyEnrichmentAt":254,"extractAt":255,"githubAt":254,"llmAt":256,"updatedAt":256},1778054813688,1778054812528,1778054896678,{"_creationTime":258,"_id":259,"community":260,"display":261,"identity":271,"providers":273,"relations":277,"workflow":279},1778053440456.6584,"k17120x7me8p1n30wxpg972esx866b8q",{"reviewCount":8},{"description":262,"installMethods":263,"name":264,"sourceUrl":265,"tags":266},"Transcribe audio to text using ElevenLabs Scribe. Supports batch transcription, realtime streaming from URLs, microphone input, and local files.",{},"ElevenLabs Speech-to-Text","https://github.com/elevenlabs/skills/tree/HEAD/openclaw/elevenlabs-transcribe",[14,15,267,268,269,270],"elevenlabs","python","realtime","batch",{"githubOwner":267,"githubRepo":191,"locale":24,"slug":272,"type":193},"elevenlabs-transcribe",{"extract":274,"llm":276},{"commitSha":275,"license":199},"b476f0ccf4be0e22b2e77cc39307665425d1472b",{"promptVersionExtension":170,"promptVersionScoring":171,"score":216,"targetMarket":176,"tier":177},{"repoId":278},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"anyEnrichmentAt":280,"extractAt":281,"githubAt":280,"llmAt":282,"updatedAt":282},1778053440833,1778053440456,1778053480675,{"_creationTime":284,"_id":285,"community":286,"display":287,"identity":297,"providers":300,"relations":304,"workflow":306},1778054691785.2515,"k17ev68gbw25zazp0w5z2a61hd8662cc",{"reviewCount":8},{"description":288,"installMethods":289,"name":290,"sourceUrl":291,"tags":292},"Implement speech-to-text (ASR/automatic speech recognition) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to transcribe audio files, convert speech to text, build voice input features, or process audio recordings. Supports base64 encoded audio files and returns accurate text transcriptions.",{},"ASR (Speech to Text) Skill","https://github.com/answerzhao/agent-skills/tree/HEAD/glm-skills/ASR",[293,294,14,295,296,15],"asr","speech-to-text","sdk","cli",{"githubOwner":298,"githubRepo":299,"locale":24,"slug":293,"type":193},"answerzhao","agent-skills",{"extract":301,"llm":303},{"commitSha":302,"license":199},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":170,"promptVersionScoring":171,"score":250,"targetMarket":176,"tier":177},{"repoId":305},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":307,"extractAt":308,"githubAt":307,"llmAt":309,"updatedAt":309},1778054692243,1778054691785,1778054738050,{"_creationTime":311,"_id":312,"community":313,"display":314,"identity":320,"providers":321,"relations":324,"workflow":325},1778053440456.66,"k176861yt3z945kzntpp4a5m95866aq8",{"reviewCount":8},{"description":315,"installMethods":316,"name":264,"sourceUrl":317,"tags":318},"Transcribe audio to text using ElevenLabs Scribe v2. Use when converting audio/video to text, generating subtitles, transcribing meetings, or processing spoken content.",{},"https://github.com/elevenlabs/skills/tree/HEAD/speech-to-text",[14,15,267,319,294],"api",{"githubOwner":267,"githubRepo":191,"locale":24,"slug":294,"type":193},{"extract":322,"llm":323},{"commitSha":275,"license":199},{"promptVersionExtension":170,"promptVersionScoring":171,"score":250,"targetMarket":176,"tier":177},{"repoId":278},{"anyEnrichmentAt":280,"extractAt":281,"githubAt":280,"llmAt":282,"updatedAt":282},{"_creationTime":327,"_id":328,"community":329,"display":330,"identity":341,"providers":344,"relations":349,"workflow":351},1778054035325.875,"k1786xrb93cze519jccqw2h6hx867q00",{"reviewCount":8},{"description":331,"installMethods":332,"name":333,"sourceUrl":334,"tags":335},"Video and audio processing with FFmpeg. Use for format conversion, resizing, compression, audio extraction, and preparing assets for Remotion. Triggers include converting GIF to MP4, resizing video, extracting audio, compressing files, or any media transformation task.",{},"FFmpeg for Video Production","https://github.com/digitalsamba/claude-code-video-toolkit/tree/HEAD/.claude/skills/ffmpeg",[336,16,15,337,338,339,340],"ffmpeg","media","remotion","processing","conversion",{"githubOwner":342,"githubRepo":343,"locale":24,"slug":336,"type":193},"digitalsamba","claude-code-video-toolkit",{"extract":345,"llm":348},{"commitSha":346,"license":347},"dc1bbd251ef137bde9cf460bacb88f13adb3a808","MIT-0",{"promptVersionExtension":170,"promptVersionScoring":171,"score":250,"targetMarket":176,"tier":177},{"repoId":350},"kd77w77a4w1f7nnb9v4fmh2eb1865dn1",{"anyEnrichmentAt":352,"extractAt":353,"githubAt":352,"llmAt":354,"updatedAt":354},1778054036248,1778054035325,1778054079849,{"_creationTime":356,"_id":357,"community":358,"display":359,"identity":367,"providers":368,"relations":372,"workflow":373},1778054035325.8745,"k178gqcwez20sdn3tt9v878bf5866y07",{"reviewCount":8},{"description":360,"installMethods":361,"name":362,"sourceUrl":363,"tags":364},"Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.",{},"ElevenLabs Audio Generation","https://github.com/digitalsamba/claude-code-video-toolkit/tree/HEAD/.claude/skills/elevenlabs",[15,365,366,267,338,16,268],"voiceover","tts",{"githubOwner":342,"githubRepo":343,"locale":24,"slug":267,"type":193},{"extract":369,"llm":370},{"commitSha":346,"license":199},{"promptVersionExtension":170,"promptVersionScoring":171,"score":371,"targetMarket":176,"tier":177},93,{"repoId":350},{"anyEnrichmentAt":352,"extractAt":353,"githubAt":352,"llmAt":354,"updatedAt":354}]